检索结果-内蒙古大学图书馆

Low Rank Reduced Biquaternion Tensor Ring Decomposition and Tensor Completion

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Luo, Hui Liu, Xin Liu, Wei Zhang, Yang School of Computer Science and Engineering Faculty of Innovation Engineering Macau University of Science and Technology Avenida Wai Long TaiPa 999078 China Macau Institute of Systems Engineering Faculty of Innovation Engineering Macau University of Science and Technology Avenida Wai Long TaiPa 999078 China School of Artificial Intelligence Sun Yat-sen University The Guangdong Key Laboratory of Big Data Analysis and Processing No.135 West Xingang Road Guangdong Provience Guangzhou510275 China Department of Mathematics University of Manitoba No.135 West Xingang Road WinnipegMBR3T 2N2 Canada

Reduced biquaternions (RBs), as an extension of complex numbers, have demonstrated exceptional capabilities in digital signal and image processing. They not only excel particularly in encoding color information but also feature multiplicative commutativity, which simplify the theoretical analysis of related algorithms. Concurrently, tensor completion methods based on tensor ring decomposition in the real domain have been proven effective in exploiting low-rank structures. Building upon these insights, this paper first introduces the Reduced Biquaternion Tensor Ring (RBTR) decomposition, along with a detailed exposition of the corresponding algorithm RBTR-SVD. Leveraging RBTR decomposition, we propose a novel low-rank tensor completion algorithm RBTR-TV integrating RBTR rank with Total Variation (TV) regularization to optimize the process. In color image completion tasks, our method exhibits remarkable stability and robustness, outperforming traditional methods, especially if there are a lot of missing data in the image. © 2024, The Authors. All rights reserved.

关键词： Tensors

Dual attention mechanism object tracking algorithm based on Fully-convolutional Siamese network

学校读者我要写书评

暂无评论

Dual attention mechanism object tracking algorithm based on ...

International Conference on Networking and Network Applications (NaNA)

作者： Sugang Ma Zixian Zhang Lei Zhang Yanping Chen Xiaobao Yang Lei Pu Zhiqiang Hou School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an Shaanxi China School of Information Engineering Chang’an University Xi’an Shaanxi China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an Key Laboratory of Big Data and Intelligent Computing Xi’an University of Posts and Telecommunications Xi’an Shaanxi China School of Information and Navigation Air Force Engineering University Xi’an Shaanxi China

In an effort to the problem of insufficient tracking performance of the Fully-convolutional Siamese network (SiamFC) in complex scenarios, a dual attention mechanism object tracking algorithm based on the Fully-convolutional Siamese network is proposed to improve the generalization capability of the tracker by ameliorating the robustness of the template characteristics. Firstly, a global context attention module is appended after the backbone network of SiamFC to ameliorate the power of original feature extraction from two dimensions of spatial and channel. Then, a coordinate attention module is introduced to augment the capability of feature extraction in the channel dimension. Finally, the model of the proposed algorithm is trained on the Got-10k dataset. Five related algorithms are tested on the OTB2015 dataset, the results of experiments manifest that our algorithm outperforms the baseline trackers, the success and precision rate of the proposed algorithm are improved by 3.3% and 6.3%. The average tracking speed is 145FPS, which can demand the requirement of real-time tracking.

关键词： Target tracking Feature extraction Real-time systems Robustness Object tracking Task analysis

Instance-wise graph-based framework for multivariate time series forecasting

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Xu, Wentao Liu, Weiqing Bian, Jiang Yin, Jian Liu, Tie-Yan School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Microsoft Research Asia Beijing China School of Artificial Intelligence Sun Yat-Sen University Zhuhai China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Microsoft Research Asia

The multivariate time series forecasting has attracted more and more attention because of its vital role in different fields in the real world, such as finance, traffic, and weather. In recent years, many research efforts have been proposed for forecasting multivariate time series. Although some previous work considers the interdependencies among different variables in the same timestamp, existing work overlooks the inter-connections between different variables at different time stamps. In this paper, we propose a simple yet efficient instance-wise graph-based framework to utilize the inter-dependencies of different variables at different time stamps for multivariate time series forecasting. The key idea of our framework is aggregating information from the historical time series of different variables to the current time series that we need to forecast. We conduct experiments on the Traffic, Electricity, and Exchange-Rate multivariate time series datasets. The results show that our proposed model outperforms the state-of-the-art baseline methods. © 2021, CC BY.

关键词： Time series

Structure-aware random fourier kernel for graphs 21

学校读者我要写书评

暂无评论

Structure-aware random fourier kernel for graphs

Proceedings of the 35th International Conference on Neural Information processing Systems

作者： Jinyuan Fang Qiang Zhang Zaiqiao Meng Shangsong Liang School of Computer Science and Engineering Sun Yat-sen University China and Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Hangzhou Innovation Center Zhejiang University China and College of Computer Science and Technology Zhejiang University China and AZFT Knowledge Engine Lab China School of Computing Science University of Glasgow United Kingdom and Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates School of Computer Science and Engineering Sun Yat-sen University China and Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China and Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates

ISBN: (纸本)9781713845393

Gaussian Processes (GPs) define distributions over functions and their generalization capabilities depend heavily on the choice of kernels. In this paper, we propose a novel structure-aware random Fourier (SRF) kernel for GPs that brings several benefits when modeling graph-structured data. First, SRF kernel is defined with a spectral distribution based on the Fourier duality given by the Bochner's theorem, transforming the kernel learning problem to a distribution inference problem. Second, SRF kernel admits a random Fourier feature formulation that makes the kernel scalable for optimization. Third, SRF kernel enables to leverage geometric structures by taking subgraphs as inputs. To effectively optimize GPs with SRF kernel, we develop a variational EM algorithm, which alternates between an inference procedure (E-step) and a learning procedure (M-step). Experimental results on five real-world datasets show that our model can achieve state-of-the-art performance in two typical graph learning tasks, i.e., object classification and link prediction.

关键词：

Optimizing the numbers of queries and replies in federated learning with differential privacy

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhou, Yipeng Liu, Xuezheng Fu, Yao Wu, Di Li, Chao Yu, Shui The Department of Computing Faculty of Science and Engineering Macquarie University SydneyNSW2109 Australia The School of Data and Computer Science Sun Yat-sen University Guangzhou510275 China The Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China Co. Ltd China The School of Computer Science University of Technology Sydney Australia

Federated learning (FL) empowers distributed clients to collaboratively train a shared machine learning model through exchanging parameter information. Despite the fact that FL can protect clients' raw data, malicious users can still crack original data with disclosed parameters. To amend this flaw, differential privacy (DP) is incorporated into FL clients to disturb original parameters, which however can significantly impair the accuracy of the trained model. In this work, we study a crucial question which has been vastly overlooked by existing works: what are the optimal numbers of queries and replies in FL with DP so that the final model accuracy is maximized. In FL, the parameter server (PS) needs to query participating clients for multiple global iterations to complete training. Each client responds a query from the PS by conducting a local iteration. Our work investigates how many times the PS should query clients and how many times each client should reply the PS. We investigate two most extensively used DP mechanisms (i.e., the Laplace mechanism and Gaussian mechanisms). Through conducting convergence rate analysis, we can determine the optimal numbers of queries and replies in FL with DP so that the final model accuracy can be maximized. Finally, extensive experiments are conducted with publicly available datasets: MNIST and FEMNIST, to verify our analysis and the results demonstrate that properly setting the numbers of queries and replies can significantly improve the final model accuracy in FL with DP. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

SEEK: Segmented Embedding of Knowledge Graphs

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Xu, Wentao Zheng, Shun He, Liang Shao, Bin Yin, Jian Liu, Tie-Yan School of Data and Computer Science Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Microsoft Research Asia Beijing China

In recent years, knowledge graph embedding becomes a pretty hot research topic of artificial intelligence and plays increasingly vital roles in various downstream applications, such as recommendation and question answering. However, existing methods for knowledge graph embedding can not make a proper trade-off between the model complexity and the model expressiveness, which makes them still far from satisfactory. To mitigate this problem, we propose a lightweight modeling framework that can achieve highly competitive relational expressiveness without increasing the model complexity. Our framework focuses on the design of scoring functions and highlights two critical characteristics: 1) facilitating sufficient feature interactions;2) preserving both symmetry and antisymmetry properties of relations. It is noteworthy that owing to the general and elegant design of scoring functions, our framework can incorporate many famous existing methods as special cases. Moreover, extensive experiments on public benchmarks demonstrate the efficiency and effectiveness of our framework. Source codes and data can be found at https://***/Wentao-Xu/SEEK. Copyright © 2020, The Authors. All rights reserved.

关键词： Knowledge graph

EXISTENCE AND CONTROLLABILITY FOR NONLINEAR FRACTIONAL CONTROL SYSTEMS WITH DAMPING IN HILBERT SPACES

学校读者我要写书评

暂无评论

Acta Mathematica Scientia 2019年第1期39卷 229-242页

作者： Xiuwen LI Zhenhai LIU Jing LI Chris TISDELL School of Science Nanjing University of Sciences and Technology Guangxi Colleges and Universities Key Laboratory of Complex System Optimization and Big Data Processing Yulin Normal University Hunan Province Key Laboratory of Mathematical Modelling and Analysis in Engineering Department of Mathematics and Statistics Changsha University of Science and Technology Faculty of Science The University of New South Wales UNSW

In this paper, we are concerned with the existence of mild solution and controllability for a class of nonlinear fractional control systems with damping in Hilbert *** first step is to give the representation of mild solution for this control system by utilizing the general method of Laplace transform and the theory of(α, γ)-regularized families of operators. Next, we study the solvability and controllability of nonlinear fractional control systems with damping under some suitable sufficient conditions. Finally, two examples are given to illustrate the theory.

关键词： existence controllability fractional control systems damping regularized resolvent family

Generative Semantic Hashing Enhanced via Boltzmann Machines

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zheng, Lin Su, Qinliang Shen, Dinghan Chen, Changyou School of Data and Computer Science Sun Yat-sen University Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Microsoft Dynamics 365 AI CSE Department SUNY at Buffalo

Generative semantic hashing is a promising technique for large-scale information retrieval thanks to its fast retrieval speed and small memory footprint. For the tractability of training, existing generative-hashing methods mostly assume a factorized form for the posterior distribution, enforcing independence among the bits of hash codes. From the perspectives of both model representation and code space size, independence is always not the best assumption. In this paper, to introduce correlations among the bits of hash codes, we propose to employ the distribution of Boltzmann machine as the variational posterior. To address the intractability issue of training, we first develop an approximate method to reparameterize the distribution of a Boltzmann machine by augmenting it as a hierarchical concatenation of a Gaussian-like distribution and a Bernoulli distribution. Based on that, an asymptotically-exact lower bound is further derived for the evidence lower bound (ELBO). With these novel techniques, the entire model can be optimized efficiently. Extensive experimental results demonstrate that by effectively modeling correlations among different bits within a hash code, our model can achieve significant performance gains. Copyright © 2020, The Authors. All rights reserved.

关键词： Hash functions

Embedding dynamic attributed networks by modeling the evolution processes

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Xu, Zenan Ou, Zijing Su, Qinliang Yu, Jianxing Quan, Xiaojun Lin, Zhenkun School of Data and Computer Science Sun Yat-sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Key Lab. of Machine Intelligence and Advanced Computing Ministry of Education China

Network embedding has recently emerged as a promising technique to embed nodes of a network into low-dimensional vectors. While fairly successful, most existing works focus on the embedding techniques for static networks. But in practice, there are many networks that are evolving over time and hence are dynamic, e.g., the social networks. To address this issue, a high-order spatio-temporal embedding model is developed to track the evolutions of dynamic networks. Specifically, an activeness-aware neighborhood embedding method is first proposed to extract the high-order neighborhood information at each given timestamp. Then, an embedding prediction framework is further developed to capture the temporal correlations, in which the attention mechanism is employed instead of recurrent neural networks (RNNs) for its efficiency in computing and flexibility in modeling. Extensive experiments are conducted on four real-world datasets from three different areas. It is shown that the proposed method outperforms all the baselines by a substantial margin for the tasks of dynamic link prediction and node classification, which demonstrates the effectiveness of the proposed methods on tracking the evolutions of dynamic networks. Copyright © 2020, The Authors. All rights reserved.

关键词： Recurrent neural networks